Page History

/**
 * Job lineage is built according to StreamGraph. Users can get sources, sinks and relationships from lineage.
 */
@PublicEvolvig
public interface LineageGraph {
    /* Source lineage vertex list. */
    List<SourceLineageVertex> sources();

    /* Sink lineage vertex list. */
    List<LineageVertex> sinks();

    /* lineage edges from sources to sinks. */
    List<LineageEdge> relations();
}

/** Lineage vertex represents the connectors in lineage graph, including source and sink. */
@PublicEvolving
public interface LineageVertex {
    /* List of input (for source) or output (for sink) datasets interacted with by the connector */
    List<LineageDataset> datasets;
}

/** Lineage dataset represents the source or sink in the job. */
@PublicEvolving
public interface LineageDataset {
    /* Name for this particular dataset. */
    String name;
    /* Unique name for this dataset's storage, for example, url for jdbc connector and location for lakehouse connector. */
    String namespace;
    /* Facets for the lineage vertex to describe the particular information of dataset, such as schema and config. */ 
    Map<String, Facet> facets;
}

/** Builtin config Configfacet for the lineage vertex contains all the options for the connectordataset. */
@PublicEvolving
public interface DatasetConfigFacet {
    Map<String, String> config();
}

/** Builtin schema facet for dataset. */
@PublicEvolving
public interface DatasetSchemaFacet {
    Map<String, String> configfields();
}

/** Lineage vertex for source which has boundedness. */
@PublicEvolving
public interface SourceLineageVertex extends LineageVertex {
    /**
     * The boundedness for the source connector, users can get boundedness for each sources in
     * the lineage and determine the job execution mode with RuntimeExecutionMode.
     */
    Boundedness boundedness();
}

/** Lineage edge from sources to sink. */
@PublicEvolving
public interface LineageEdge {
    LineageVertex source();
    LineageVertex sink();
}